DATABASE OF ENGLISH-UZBEK VERBS AND PHRASAL VERBS FOR
MACHINE TRANSLATION
Abdurakhmonova Nilufar
Tashkent State University of the Uzbek Language
and Literature named after Alisher Navoi
abdurahmonova.1987@mail.ru
Abstract
. The article deals with the issues about building database for machine translation.
There are some difficulties for machine translation due to active positions in all styles of English
and the complex characteristic nature of phrasal verbs. The article also discusses all models of
English verbs and phrasal verbs to project of database.
Key words:
machine translation, database, phrasal verbs, model, computer aided dictionaries,
NLP (natural language processing).
In the process of globalization and integration the role of computer-assisted
dictionaries has been increasing widely. Reason for this is that it links up the
unification terms in different spheres of science and technology and e-learning,
information retrieval and others.
The basic units of language and speech should be included into machine
dictionary. Such units may be collocations and phraseological units. Apart from those
units main lexemes are within the vocabulary database. In general, natural language
is considered to be the most complex system of thinking. So there are different forms
of speech. First of all, we should clarify what is database for the dictionary. “The
database system-1) systematized collection of data that can be accessed immediately,
and manipulated by a data-processing system for a specific purpose; 2) (informal)
any large store of information [1].
Given this amount of data, it is not surprising that a good number of linguistics
have investigated software for managing data. Databases have long been standard
repositories in phonetics and psycholinguistics research, but their findings, increasing
further use not only in phonology, morphology, syntax, historical linguistics and
dialectology but also in areas of applied linguistics such as lexicograph y and
computer-assisted language learning [2]. We agree to this view that this is very
crucial now how to build a linguistic database for machine translation as well. There
are some database software for complex logical structures: FileMaker Pro, SQL,
Oracle database and for simple databases, software which is good at producing tables:
Microsoft Excel, Access or Microsoft Word.
For building machine translation system from English into Uzbek there should be
the computer-assisted dictionary in great size that is saved in database. Both English
and Uzbek have a very huge database consisting all linguistic layers and they are very
dissimilar. One verbal category in English is a phrasal verb. It is a real challenge for
structural components of the sentence. “Phrasal verbs are considered to be a very
important and frequently occurring feature of the English language. First of all, they
are so common in every - day conversation, and non - native speakers who wish to
sound natural when speaking this language need to learn their grammar in order to
know how to produce them correctly. Secondly, the habit of inventing phrasal
verbs has been the source of great enrichment of the language. By means of
phrasal verbs it is described the greatest variety of human actions and relations” [3, p
16]. So verb-particle constructions in English are very complex to analyse and
describe coherently in synchronic terms.
Database design is considered to be one of the stages of cycle information system
and very crucial task is normalization of each unit in the process of database design.
We have gathered more than 12 thousand phrasal verbs and their 3 thousand separate
main verbs. But every unit placed in detached cell in a database and overall qualities
of them is more than 75 thousand phrasal verbs and main verbs. This proposed
translation the direction of English-Uzbek-English.
Dostları ilə paylaş: |